Add flash attention v2 and INT4 CUDA for LLaMA E2E benchmarking #20149
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hanbitmyths
reviewed
Mar 29, 2024
onnxruntime/python/tools/transformers/models/llama/benchmark_e2e.py
Outdated
Show resolved
Hide resolved
hanbitmyths
reviewed
Mar 29, 2024
hanbitmyths
approved these changes
Mar 29, 2024
YUNQIUGUO
pushed a commit
that referenced
this pull request
Apr 2, 2024
### Description This PR adds flash attention v2 and support for INT4 CUDA benchmarking in PyTorch. ### Motivation and Context The [flash attention v2](https://github.com/Dao-AILab/flash-attention) algorithm helps improve model performance in PyTorch. Support for INT4 CUDA in PyTorch is done through the [`bitsandbytes`](https://github.com/TimDettmers/bitsandbytes) package.
TedThemistokleous
pushed a commit
to TedThemistokleous/onnxruntime
that referenced
this pull request
May 7, 2024
…osoft#20149) ### Description This PR adds flash attention v2 and support for INT4 CUDA benchmarking in PyTorch. ### Motivation and Context The [flash attention v2](https://github.com/Dao-AILab/flash-attention) algorithm helps improve model performance in PyTorch. Support for INT4 CUDA in PyTorch is done through the [`bitsandbytes`](https://github.com/TimDettmers/bitsandbytes) package.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
This PR adds flash attention v2 and support for INT4 CUDA benchmarking in PyTorch.
Motivation and Context
The flash attention v2 algorithm helps improve model performance in PyTorch. Support for INT4 CUDA in PyTorch is done through the
bitsandbytespackage.